Combined method for detecting anomalies in a water distribution system

Abstract

A method for the detection of anomalies in a networked water distribution system is provided. It improves detection methods based on an iterative modification of control variables of the network, by determining a reduced set of entities of the water distribution network on which control variables should be iteratively modifier. The invention increases the computing costs, and the reliability of such methods of detecting anomalies in a water distribution system.

Description

FIELD OF THE INVENTION[0001]The present invention relates to the detection of anomalies in a water distribution system. More specifically, it relates to the detection of anomalies with the combined use of statistics and a hydraulic model of the water distribution system.BACKGROUND PRIOR ART[0002]A system for distributing drinkable water is notably made of pipes between a water head and consumers, along with control devices such as valves and pumps. Such system can be subject to numerous anomalies. Anomalies belong to a plurality of types. Hydraulic anomalies comprise leaks, abnormal variation of pressure, fast drop of the water level of a storage tank, incoherent mass balance of storage. Operation anomalies define an element in the system which is in an incorrect state, for example a valve in an opening state different from the one stored in the information system. These anomalies, especially leaks, can dramatically reduce the performance of the water distribution system. For exampl...

AI Technical Summary

Benefits of technology

[0011]This permits an additional reduction of the computing load of the method, by reducing the number of control variables to modify.

[0051]The invention permits a precise detection of anomalies on any entity of a water distribution system, even if such entity is not equipped with sensors.

Problems solved by technology

Such system can be subject to numerous anomalies.

Hydraulic anomalies comprise leaks, abnormal variation of pressure, fast drop of the water level of a storage tank, incoherent mass balance of storage.

These anomalies, especially leaks, can dramatically reduce the performance of the water distribution system.

For example, leaks in the pipes are the cause of a loss of a significant part of the water between water head and consumers, and can make structural damages.

However, the typically large size of water distribution systems renders human detection of leaks and anomalies very difficult.

It is therefore impossible to inspect all pipes frequently at a reasonable cost.

However, sensor-based detection methods of anomalies have disadvantages as well.

They can generate a high number of false positive (alarms for events which are not actual anomalies), and lead to numerous useless and costly human interventions.

Otherwise, deploy a high density of sensors in the system could help in locating anomalies more precisely, but it is too costly.

However, the large number of parameters that have an impact on the hydraulic model, and the large number of iterations necessary to obtain a satisfactory solution may render the method complex on large water distribution systems.

Images